edu.ucar.opensky::articles:43840 UCAR/NCAR - Library OpenSky Support PO Box 3000 Boulder CO 80307-3000 opensky@ucar.edu http://opensky.ucar.edu/ homepage pointOfContact 2025-12-24T17:45:58.388674 ISO 19115-2 Geographic Information - Metadata - Part 2: Extensions for Imagery and Gridded Data ISO 19115-2:2009(E) https://n2t.net/ark:/85065/d7zs31zv https://doi.org/10.24381/cds.e2161bac https Related Dataset #1 ERA5-Land hourly data from 1950 to present https://doi.org/10.5281/zenodo.15720131 https Related Dataset #2 Data for LSE-CTSM parameter calibration and regionalization paper On using AI‐based large‐sample emulators for land/hydrology model calibration and regionalization 2025-07-01T00:00:00Z publication https://n2t.net/ark:/85065/d7zs31zv https://doi.org/10.1029/2024WR039525 Tang, Guoqiang author Wood, Andrew author Swenson, Sean author UCAR/NCAR - Library publisher AI&#8208;based model emulators have emerged as a pragmatic strategy for calibrating Earth System models or their components (e.g., land, atmosphere, ocean), circumventing the previously insurmountable hurdle of the process&#8208;heavy models' computational expense. Such emulators require large, spatially diverse data sets for training, however, which&#8212;in the land/hydrology context&#8212;contrasts with parameter estimation approaches that have traditionally emphasized optimizing model performance for individual basins, followed by similarity&#8208;based transfer schemes for parameter regionalization. Compared to calibrating basins individually, direct land/hydrology process model calibration approaches typically perform worse when trained jointly on large collections of basins. Building on insights from large&#8208;sample deep learning hydrologic modeling, this study introduces a Large&#8208;Sample Emulator (LSE) approach that unifies and streamlines process model parameter calibration and regionalization. Tested across 627 basins in the continental United States using the Community Terrestrial Systems Model (CTSM), the LSE approach consistently improves runoff predictions in all basins, outperforming the Single&#8208;Site Emulator (SSE) in both single&#8208;objective and multi&#8208;objective calibration tasks. Moreover, LSE&#8208;based regionalization in unseen basins, evaluated through spatial cross&#8208;validation, achieves better results than the default parameters in most cases. This LSE framework offers a promising strategy for effective large&#8208;domain process&#8208;based model calibration and regionalization. UCAR/NCAR - Library OpenSky Support PO Box 3000 Boulder CO 80307-3000 opensky@ucar.edu http://opensky.ucar.edu/ homepage pointOfContact PDF Text theme Resource Type 2016-01-01T00:00:00Z publication <span style="font-family:Arial;font-size:10pt;font-style:normal;" data-sheets-root="1">Copyright author(s). This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</span> None eng geoscientificInformation